Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/stefaniuk/loadoutWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/stefaniuk/loadout/spec.consolidate)<a href="https://agentmods.dev/commands/stefaniuk/loadout/spec.consolidate"><img src="https://agentmods.dev/badge/commands/stefaniuk/loadout/spec.consolidate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/stefaniuk/loadout/spec.consolidate"><img src="https://agentmods.dev/badge/commands/stefaniuk/loadout/spec.consolidate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00815 |
| Opus 5.5 | $0.00014 | $0.00326 |
| Sonnet 5.5 | $0.00007 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
spec.consolidate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
This prompt delegates to the spec-consolidation skill.
Run the spec-consolidation skill. If the user input below names a step
(spec, data-model, research, quickstart, contracts, checklists),
run only that step. Otherwise run all steps defined in the
spec-consolidation skill in order.
Use the current working tree at HEAD as the baseline unless the user
explicitly asks for the default branch or another historical view.
If the user input is invalid or incomplete (for example, an unknown step name or a baseline reference that cannot be resolved), respond with an error message that names the offending value and lists the accepted options, and do not start the consolidation run.
$ARGUMENTS
Mandatory behavioural constraints (see SKILL.md and its AGENTS.md for full detail):
Discovery and inputs
- For medium or large repos, use one read-only exploration-agent pass up front to inventory feature artefacts, overlapping capabilities, likely evidence modules, and obvious drift candidates. Reuse that inventory instead of remapping the whole repo in every step.
- Output is intent-only. Never copy or paraphrase
tasks.md. You may inspectplan.mdnarrowly for architecture context when that context is not recoverable fromspec.md,research.md,data-model.md,quickstart.md,contracts/, or the code. Never emit phases, task IDs, or implementation order intospecs/product/.
Baseline and file-handling rules
- Reconcile against the selected baseline; the baseline default is set above.
- Write only to
specs/product/. Never modify, move, or delete any existingspecs/NNN-*/directory. - Only create
specs/product/checklists/when source feature checklists exist. Otherwise skip step 06 and say so.
Content rules
- When per-feature specs disagree, the behaviour evidenced by the selected
baseline implementation and validation artefacts wins; record divergence in
specs/product/research.md. - For
quickstart.md, prefer the current repository bootstrap and operator guidance surface, entry-point declarations, runtime or packaging metadata, and executable validation artefacts when the source feature quickstarts are stale. - In consolidated checklists, leave items unchecked unless the current consolidation run actually validated them.
- Every consolidated requirement, entity, contract, and checklist item must appear in exactly one place and cite both its source spec section and the implementing code path.
Validation rules
- Validate
specs/product/**first, then run broader repo gates if available. If repo-wide validation fails for unrelated pre-existing issues, report that separately from any new product-doc failures.
Final-message rules
- After completion, include a concise before/after analysis in the final assistant message: fragmentation before, improvements after, remaining risks, and confidence that the product set matches the selected baseline.
- After completion, list (in the final assistant message) any duplicate
derived artefacts that now have a product-facing counterpart and could be
archived after review. Do not recommend deleting the
specs/NNN-*feature histories themselves.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 80 lines · 35 tokens per session scan A 55d4b94f7353
spec.consolidate is a command published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 13d ago), licensed MIT. It adds 35 tokens to every session and 815 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other commands, from other repositories
sddp-implement-qc-loop
Command description: Run implement and QC in a continuous loop. Argument hint: [optional: feature directory or branch name] Command category: orchestration Prerequisites: spec, plan, tasks.
sddp-plan
Command description: Create an implementation plan from the current feature specification. Argument hint: [optional: planning constraints or focus areas] Command category: feature-delivery Prerequisites: spec.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
sddp-qc
Command description: Run quality control against the implemented feature. Argument hint: [optional: testing focus such as unit tests, security audit, requirements sync] Command category: feature-delivery Prerequisites: spec, plan, tasks, implementation:complete.
sddp-specify
Command description: Create a feature specification from a feature description. Argument hint: [feature description] Command category: feature-delivery Prerequisites: project-instructions.
sddp-amend
Command description: Propagate a bootstrap change across canonical project artifacts and the project plan. Argument hint: [project-level change to propagate across bootstrap artifacts] Command category: project-bootstrap Prerequisites: project-instructions, product-document, technical-context, project-plan.